Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13590
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and military alliances

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.27
    1.2%
    288
    +0.17
    0.7%
    681
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    681
    +0.27
    0.09
    706
    +0.17
    0.09
    288
    +0.12
    0.16
    Negative Logits
    ials
    -0.77
    hibited
    -0.71
    lycer
    -0.70
    Magikarp
    -0.69
    phies
    -0.69
    perature
    -0.68
    hib
    -0.67
    agate
    -0.67
    iple
    -0.66
    ambling
    -0.66
    POSITIVE LOGITS
    naire
    1.01
     partners
    1.01
     partner
    0.94
     coalition
    0.87
     partnered
    0.87
     alliance
    0.81
     alliances
    0.79
     mates
    0.78
     Aven
    0.78
     member
    0.77
    Activations Density 6.317%

    No Known Activations